CN106815551B - A kind of optimization method of the variation function parameter fitting of forest inventory control - Google Patents
A kind of optimization method of the variation function parameter fitting of forest inventory control Download PDFInfo
- Publication number
- CN106815551B CN106815551B CN201611121281.1A CN201611121281A CN106815551B CN 106815551 B CN106815551 B CN 106815551B CN 201611121281 A CN201611121281 A CN 201611121281A CN 106815551 B CN106815551 B CN 106815551B
- Authority
- CN
- China
- Prior art keywords
- data
- particle
- value
- variable parameter
- forest
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Mining
Abstract
The invention discloses a kind of optimization methods of the variation function parameter fitting of forest inventory control, the remote sensing image data of the forest reserves is obtained by satellite, data statistics and quantification treatment are carried out using terminal to sampling region, carry out particle of data group optimization, partition clustering is carried out to variable parameter collection using K mean value division methods, variable parameter is fitted；The optimization of variation function parameter fitting is carried out using characteristic vector of the support vector regression method to sampling region multidimensional.The multi- source Remote Sensing Data data of method of the invention for the various multidates, different resolution, multi-spatial scale of domestic and international satellite system at present, forest department at different levels can be better met after optimization to the needs of forest inventory control informationization, achieve the purpose that reinforce forest inventory control, while can also realize timely updating and interim governing plan for forest resource data.
Description
Technical field
It is specifically to be related to a kind of variation letter of forest inventory control the invention belongs to variation function optimisation technique field
The optimization method of number parameter fitting.
Background technique
The forest reserves are the material bases of production of forestry, and Forest Resources Condition is to measure the most important mark of work on forestry effect
Will.For forest because being influenced by artificial business activities and natural cause in development process, the forest reserves are in growth and decline state change always
Among change, therefore, it is necessary to reinforce the management and supervision to the forest reserves, scientific and effective management system is established.Forest reserves pipe
The object of reason is mainly forest land, forest, wild animals and plants and forest environment.
Variation function refers to the mathematic expectaion of regionalized variable increment square, the i.e. variance of regionalized variable increment.It is typical
Variation function curve is divided into parabolic type (continuous type), lienar for, discontinuous form (block metal type), stochastic pattern (pure piece of metal type), transformation
Type, they represent the variability with the geologic body parameter of different continuitys and randomness.The experiment actually calculated becomes
Different 2 γ * (h) of function is in the N being separated by with vector h between the average value of increment square two observations of point, i.e. 2 γ * (h)=
1N (h) ∑ N (h) i=1 (Z (xi+h) Z (xi)) 22 γ * (h) are increment variance half, are called semivariable function, and referred to as make a variation letter
Number.
After support vector regression method mainly passes through liter dimension, it is linear to realize that linear decision function is constructed in higher dimensional space
It returns, when function insensitive with e, basis is mainly the insensitive function of e and Kernels.If by the mathematical model table of fitting
It is up to a certain curve of hyperspace, then resulting according to the insensitive function of e as a result, being exactly " the e pipe for including the curve and training points
Road ".In all sample points, that a part of sample point being only distributed on " tube wall " determines the position of pipeline.This part
Training sample is known as " supporting vector ".For the non-linear of adaptation training sample set, traditional approximating method is usually in linear side
Add higher order term behind journey.This method is really effective, but thus increased adjustable parameter increases the risk of over-fitting rather.Support to
Amount regression algorithm solves this contradiction using kernel function.Replace the linear term in linear equation that can make original line with kernel function
Property algorithm " non-linearization ", can do nonlinear regression.At the same time, it introduces kernel function and has achieved the purpose that " rising dimension ", and increase
The adjustable parameter added is that over-fitting still can control.A spotlight in support vector machines is mentioned in traditional optimization problem
Go out duality theory, mainly there is minimax antithesis and Lagrange duality.
It is typically difficult to divide in lower dimensional space vector set when handling the variation function parameter of forest inventory control, solution
Method is to map them into higher dimensional space.But this method bring difficulty is exactly the increase of computation complexity, and kernel function
Just dexterously solves this problem.As long as that is, selecting kernel function appropriate, so that it may obtain point of higher dimensional space
Class function.After kernel function has been determined, due to determining the given data of kernel function, there is also certain errors, it is contemplated that promotes
Property problem, it is therefore necessary to the parameter of variation function is optimized in fit procedure, make its numerical value infinite approach most just when.
Summary of the invention
The technical problem to be solved by the present invention is to provide a kind of optimizations of the variation function parameter fitting of forest inventory control
The parameter of corresponding variation function is mainly passed through multiplicity during forest inventory control by method in fit procedure
It is handled according to analysis, using optimization methods such as particle group optimizing, support vector regressions, the value range of variation function is reached more with this
Add the effect of precision.
Technical scheme is as follows:
A kind of optimization method of the variation function parameter fitting of forest inventory control, mainly comprises the steps that
(1) remote sensing image that the forest reserves are obtained by satellite, pre-processes the remote sensing image, obtains pre- place
Remote sensing image data after reason carries out data statistics and quantification treatment using terminal to sampling region；
(2) particle of data group optimization is carried out for the data of the obtained forest reserves, using K mean value division methods to variable
Parameter set carries out partition clustering, obtains the cluster result of data set, is fitted according to fitness value formula to variable parameter；
(3) the specific data value of variable parameter collection and adaptive optimal control angle value are generated into characteristic vector within the scope of allowable error
And the characteristic vector for reflecting sampling regional space feature, using support vector regression method to the Characteristic Vectors of sampling region multidimensional
Amount carries out the optimization of variation function parameter fitting.
Further, the data statistics and quantification treatment refer to the remote sensing shadow for obtaining pretreatment according to remote sensing image
As being overlapped with pre-stored position vector data, spanning forest remote sensing image geography information figure uses terminal
The region for needing data to analyze is carried out coordinate axiom division by the data statistics to hum pattern, and the grid cell of formation is according to right
That answers ratio is classified as unit amount, selects fixed area to be sampled in the region, the concrete shape in region of sampling does not have
It requires, sampling area data can accurately be obtained by being subject to, and not limit to the dimension in sampling region, then be explored using interpolation method
The spatial variability structure of the data of analyzed area, fitting generate the theoretical variation function of each variable parameter, the variable ginseng
Number is that corresponding generate is converted according to needs of production.
Further, particle of data group optimization is that the value range progress of variable parameter is obtained according to area data
Classification, and sorted variable parameter collection is obtained, specific data value, allowable error, data are determined for each variable parameter collection
Amount is encoded using the data that variable parameter of the particle coding mode to selection is concentrated, sets the number of particle in particle populations
The search space range of mesh and maximum number of iterations, the position and speed of entire particle populations, sets the initial bit of each particle
It sets and speed is drawn according to the serial number of the value of each dimension of current particle coding site acquisition initial cluster center submanifold using K mean value
Method is divided to carry out partition clustering to variable parameter collection, it is two elements in Euclidean space that the K mean value division methods, which refer to,
Aggregate distance, for identifying the distinctiveness ratio of two scaling elements, formula are as follows:The cluster result for obtaining data set, according to fitness value public affairs
Formula calculates variable parameter clustering result the fitness value of particle, judges current particle fitness value and particle populations most
The size of excellent fitness value replaces particle populations adaptive optimal control angle value current particle fitness value if being less than, by particle
Population optimal location is replaced with current particle position, otherwise constant, and it is preset to judge whether particle group optimizing the number of iterations reaches
Maximum number of iterations exports particle populations adaptive optimal control angle value and corresponding variable parameter collection class cluster is drawn if so, stopping iteration
Divide as a result, otherwise, return continues to calculate.
Further, the support vector regression method refers to the feature using support vector regression to sampling region multidimensional
Vector is trained, the region finally generated using the support vector regression training pattern that training obtains to theoretically variation function
Data are tested, and the predicted value of theoretic each multidimensional region figure is obtained, so that carrying out optimum theory data passes through variation
For function in the situation of change of actually sampling provincial characteristics, true reflection objectively evaluates correlation of the situation with subjective perception, excellent
Point is that the characteristic vector information of the stereo-picture obtained has stronger stability and can preferably reflect the view of stereo-picture
Feel comfort level situation of change, seeks the difference under each corresponding multi-dimensional direction of sampling regional graphics respectively according to above step
Variation function value after the corresponding optimization of space interval, using variation function value as Y-axis, space interval is X-axis, establishes mapping and closes
System, specific mapping relations quantity is related according to the regional graphics dimension of selection, obtains one and theoretical values best fit
Figure carries out recurrence calculating using linear equation, obtains the local optimum space scale under degree of fitting and each dimension, all
Dimension image, which combines, forms corresponding optimum mutation function corresponding region figure.
Further, the interpolation method uses Kriging regression method, considers and retouches during data gridding
The space correlation property for stating object, make interpolation result it is more scientific, closer to actual conditions, the error of interpolation can be provided, make to insert
The degree of reliability of value is very clear, and interpolation variance just refers to the number of both actual parameter value zv and estimated value zv* deviation square
Term hopes:
And the zv* of interpolation point is obtained by N number of discrete point；
Wherein λ and N number of discrete point refer to weighting coefficient.
Further, the dimension refers to Spatial Dimension, is actual distribution feature and map according to geographic object
Expression needs to determine, comprising: 0 dimension, 1 dimension, 2 dimensions, 2.5 peacekeepings 3 dimension.
Further, the iteration refers to the data positioning most begun to use according to particle fitness value as next time
The reference point locations of iteration, as reference point is closer to true position, the position of data positioning also can be unlimited close to true
Position.In an iterative process, data positioning, can be in different dimensional spaces to institute not by linear or non-linear attributes constraints
Some subfield values are iterated, and are compensated with this to non-linear attributes.
Further, the calculation method of the linear equation is least square method.
Further, the range of linearity of the variation function is parabolic type, lienar for, discontinuous form, stochastic pattern, transformation
The one such or several combination of type.
Compared with prior art, the method have the advantages that: pass through satellite obtain the forest reserves remote sensing shadow
As data, data statistics and quantification treatment are carried out using terminal to sampling region, for the number of the obtained forest reserves
According to particle of data group optimization is carried out, partition clustering is carried out to variable parameter collection using K mean value division methods, obtains the poly- of data set
Class is as a result, be fitted variable parameter according to fitness value formula；By the specific data value and adaptive optimal control of variable parameter collection
Angle value generates characteristic vector and the characteristic vector for reflecting sampling regional space feature within the scope of allowable error, utilizes support
Vector regression method carries out the optimization of variation function parameter fitting to the characteristic vector of sampling region multidimensional；Method of the invention is directed to
The multi- source Remote Sensing Data data of the various multidates of satellite system, different resolution, multi-spatial scale both at home and abroad at present, can be with after optimization
Forest department at different levels are better met to the needs of forest inventory control informationization, achieve the purpose that reinforce forest inventory control,
Timely updating and interim governing plan for forest resource data can also be realized simultaneously.
Detailed description of the invention
Fig. 1 is a kind of optimization method process signal of the variation function parameter fitting of forest inventory control of the present invention
Figure.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with attached drawing of the invention,
Technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is the present invention one
Divide embodiment, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making
Every other embodiment obtained, shall fall within the protection scope of the present invention under the premise of creative work.
In order to facilitate understanding of embodiments of the present invention, below in conjunction with the accompanying drawings and the specific embodiments for further solved
Explanation is released, embodiment does not constitute the restriction to the embodiment of the present invention.
Resource management is carried out according to the attribute data of the wood land in certain mountain area, wherein attribute data includes: ground class, tree
Kind, the age of stand, strain number, pest and disease damage situation, the optimization method of the variation function parameter fitting of one of forest inventory control, mainly
The following steps are included:
(1) remote sensing image that the forest reserves are obtained by satellite, pre-processes the remote sensing image, obtains pre- place
Remote sensing image data after reason carries out data statistics and quantification treatment using terminal to sampling region；The data
Statistics and quantification treatment refer to the remote sensing image for obtaining pretreatment according to remote sensing image and pre-stored position vector data
It is overlapped, spanning forest remote sensing image geography information figure, the data statistics using terminal to hum pattern will need to count
Coordinate axiom division is carried out according to the region of analysis, the grid cell of formation is classified as unit amount according to corresponding ratio, described
Region in selection fixed area be sampled, the concrete shape in region of sampling does not require, can accurately obtain sampled area
Subject to numeric field data, do not limit to the dimension in sampling region, then utilizes the spatial variability knot of the data in interpolation method Exploring Analysis region
Structure, fitting generate the theoretical variation function of each variable parameter, and the variable parameter is according to needs of production conversion pair
It should generate.
It when realizing this step, can be accomplished by the following way: obtain the remote sensing image of the forest reserves, to remote sensing shadow
As carrying out waveband selection and operation, the first remote sensing images of the forest reserves are obtained, wherein in the remote sensing image for obtaining forest resourceies
When, the resolution ratio of remote sensing image, spectral band, imaging period, sensor can be selected according to specific needs；It is right
First remote sensing images carry out radiation intensification, geometric correction, contrast adjustment, space enhancing and image co-registration processing, and it is distant to obtain second
Feel image, the information more horn of plenty of the image after making interpretation, to improve visual effect.By remote sensing image forest form map Zhong Ge bottom class
Characteristic is compared to the attribute data of the corresponding bottom class in forest resource database, judges that the attribute data of each bottom class is
It is no to change；
(2) particle of data group optimization is carried out for the data of the obtained forest reserves, using K mean value division methods to variable
Parameter set carries out partition clustering, obtains the cluster result of data set, is fitted according to fitness value formula to variable parameter；Institute
The particle of data group optimization stated is to obtain the value range of variable parameter according to area data to classify, and obtain sorted
Variable parameter collection determines specific data value, allowable error, data volume for each variable parameter collection, using particle coding mode
The data concentrated to the variable parameter of selection encode, and set the number and maximum number of iterations of particle in particle populations, whole
The search space range of the position and speed of a particle populations sets the initial position and speed of each particle, according to current grain
The value of sub- each dimension of coding site obtains the serial number of initial cluster center submanifold, using K mean value division methods to variable parameter collection
Partition clustering is carried out, the K mean value division methods refer to the aggregate distance for being two elements in Euclidean space, for identifying two
The distinctiveness ratio of a scaling element, formula are as follows:Obtain data
The cluster result of collection calculates variable parameter clustering result the fitness value of particle according to fitness value formula, and judgement is current
The size of the adaptive optimal control angle value of particle fitness value and particle populations, by particle populations adaptive optimal control angle value with working as if being less than
Preceding particle fitness value replacement, particle populations optimal location current particle position is replaced, otherwise constant, judges that population is excellent
Change whether the number of iterations reaches preset maximum number of iterations, if so, stopping iteration, exports particle populations adaptive optimal control angle value
With corresponding variable parameter collection class cluster division result, otherwise, return continues to calculate.
Forest inventory control data-optimized systems are researched and developed using C# and ArcEngineSDK, for the forest reserves
Ground class, tree species, the age of stand, strain number, pest and disease damage situation need to back up legacy data library before more new data, and data update
It finishes, ultimately forms forest resource database next year.It is all stored in the forest resource database in each year from building
The data for all forest inventory controls that library starts.
(3) the specific data value of variable parameter collection and adaptive optimal control angle value are generated into characteristic vector within the scope of allowable error
And the characteristic vector for reflecting sampling regional space feature, using support vector regression method to the Characteristic Vectors of sampling region multidimensional
Amount carries out the optimization of variation function parameter fitting, and the support vector regression method refers to using support vector regression to sampled area
The characteristic vector of domain multidimensional is trained, and the support vector regression training pattern finally obtained using training is to the letter that theoretically makes a variation
The area data that number generates is tested, and the predicted value of theoretic each multidimensional region figure is obtained, to carry out optimum theory
For data by variation function in the situation of change of actually sampling provincial characteristics, true reflection objectively evaluates situation and subjective perception
Correlation, advantage is that the characteristic vector information of the stereo-picture obtained has and stronger stability and can preferably reflect vertical
The visual comfort situation of change of body image seeks each corresponding multidimensional side of sampling regional graphics according to above step respectively
Variation function value after the corresponding optimization in downward different spaces interval, using variation function value as Y-axis, space interval is X-axis, is built
Vertical mapping relations, specific mapping relations quantity is related according to the regional graphics dimension of selection, obtains one with theoretical values most
The figure of good fitting carries out recurrence calculating using linear equation, obtains the local optimum space ruler under degree of fitting and each dimension
Degree combines all dimension images and forms corresponding optimum mutation function corresponding region figure.
Wherein, the interpolation method uses Kriging regression method, and description pair is considered during data gridding
The space correlation property of elephant, make interpolation result it is more scientific, closer to actual conditions, the error of interpolation can be provided, make interpolation
The degree of reliability is very clear, and interpolation variance just refers to the mathematics phase of both actual parameter value zv and estimated value zv* deviation square
It hopes:
And the zv* of interpolation point is obtained by N number of discrete point；
Wherein λ and N number of discrete point refer to weighting coefficient.
Wherein, the iteration refers to that the data most begun to use are positioned according to particle fitness value as next iteration
Reference point locations, as reference point is closer to true position, the position of data positioning also can be unlimited close to true position.
In an iterative process, data positioning, can be in different dimensional spaces to all not by linear or non-linear attributes constraints
Subfield value is iterated, and is compensated with this to non-linear attributes.The calculation method of the linear equation is minimum two
Multiplication.The range of linearity of the variation function is stochastic pattern.
It should be noted last that the above examples are only used to illustrate the technical scheme of the present invention and are not limiting, although ginseng
It is described the invention in detail according to preferred embodiment, those skilled in the art should understand that, it can be to the present invention
Technical solution be modified or replaced equivalently, without departing from the spirit and scope of the technical solution of the present invention.
Claims (2)
1. a kind of optimization method of the variation function parameter fitting of forest inventory control, which comprises the following steps:
(1) remote sensing image that the forest reserves are obtained by satellite, pre-processes the remote sensing image, after obtaining pretreatment
Remote sensing image data, data statistics and quantification treatment are carried out using terminal to sampling region；
(2) particle of data group optimization is carried out for the data of the obtained forest reserves, using K mean value division methods to variable parameter
Collection carries out partition clustering, obtains the cluster result of variable parameter collection, is fitted according to fitness value formula to variable parameter；
(3) the specific data value of variable parameter collection and adaptive optimal control angle value are generated into characteristic vector and use within the scope of allowable error
In reflection sampling regional space feature characteristic vector, using support vector regression method to sampling region multidimensional characteristic vector into
The optimization of row variation function parameter fitting；
The data statistics and quantification treatment refers to will pre-process obtained remote sensing image and is stored in advance according to remote sensing image
Position vector data be overlapped, spanning forest remote sensing image geography information figure, using terminal to geographical hum pattern
Data counted, the region that data will be needed to analyze carries out coordinate axiom division, in the described area for needing data to analyze
Fixed area is selected to be sampled in domain, the concrete shape in region of sampling does not require, can accurately obtain sampling number of regions
Subject to, do not limit to the dimension in sampling region, the space of the data in the region for needing data to analyze then is explored using interpolation method
Variant structure, fitting generate the theoretical variation function of each variable parameter, and the variable parameter is according to needs of production
The corresponding generation of conversion；
The particle of data group optimization is that the value range for obtaining variable parameter according to sampling area data is classified, and is obtained
To sorted variable parameter collection, specific data value, allowable error, data volume are determined for each variable parameter collection, using grain
The data that sub- coding mode concentrates the variable parameter of selection encode, and the number and maximum for setting particle in particle populations change
The search space range of the position and speed of generation number, entire particle populations sets the initial position and speed of each particle, root
The serial number that initial cluster center submanifold is obtained according to the value of each dimension of current particle coding site, using K mean value division methods to change
It measures parameter set and carries out partition clustering, the K mean value division methods refer to aggregate distance of two elements in Euclidean space, use
In the distinctiveness ratio for identifying two scaling elements, formula are as follows:
The cluster result for obtaining variable parameter collection calculates variable parameter clustering result the adaptation of particle according to fitness value formula
Angle value judges the size of the adaptive optimal control angle value of current particle fitness value and particle populations, if being less than most by particle populations
Excellent fitness value is replaced with current particle fitness value, particle populations optimal location current particle position is replaced, otherwise not
Become, judge whether particle group optimizing the number of iterations reaches preset maximum number of iterations, if so, stopping iteration, exports particle
Population adaptive optimal control angle value and corresponding variable parameter collection class cluster division result, otherwise, return continue to calculate；
The support vector regression method refers to be trained using characteristic vector of the support vector regression to sampling region multidimensional,
It is finally tested, is obtained using the area data that the support vector regression training pattern that training obtains generates theoretical variation function
To the predicted value of theoretic each multidimensional region figure, to pass through the variation feelings of variation function and practical sampling provincial characteristics
Condition carrys out optimum theory data, and true reflection objectively evaluates correlation of the situation with subjective perception, in each regional graphics of sampling
Under corresponding multi-dimensional direction, the variation function value after optimizing corresponding to different spaces interval is taken, it is empty using variation function value as Y-axis
Between between be divided into X-axis, establish mapping relations, specific mapping relations quantity is related to the regional graphics dimension of selection, obtains one
With the figure of theoretical values best fit, recurrence calculating is carried out using linear equation, obtains the office under degree of fitting and each dimension
Portion's optimal spatial scale combines the figure of all dimensions, forms the corresponding corresponding regional graphics of optimum mutation function；
The interpolation method uses Kriging regression method；
The regional graphics dimension refers to Spatial Dimension, is actual distribution feature and Map Expression according to geographic object
It needs to determine, comprising: 0 dimension, 1 dimension, 2 dimensions, 2.5 peacekeepings 3 dimension；
The iteration refers to be iterated according to particle fitness value, and the data most begun to use positioning is used as and is changed next time
The reference point locations in generation, as reference point is closer to true position, the position of data positioning also can be unlimited close to true position
It sets, in an iterative process, data positioning, can be in different dimensional spaces to all not by linear or non-linear attributes constraints
Area data be iterated, non-linear attributes are compensated with this；
The calculation method of the linear equation is least square method.
2. a kind of optimization method of the variation function parameter fitting of forest inventory control as described in claim 1, feature exist
In, the range of linearity of the variation function be one of parabolic type, lienar for, discontinuous form, stochastic pattern, transformation type or
Several combinations.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611121281.1A CN106815551B (en) | 2016-12-08 | 2016-12-08 | A kind of optimization method of the variation function parameter fitting of forest inventory control |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611121281.1A CN106815551B (en) | 2016-12-08 | 2016-12-08 | A kind of optimization method of the variation function parameter fitting of forest inventory control |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106815551A CN106815551A (en) | 2017-06-09 |
| CN106815551B true CN106815551B (en) | 2019-09-10 |
Family
ID=59106892
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611121281.1A Expired - Fee Related CN106815551B (en) | 2016-12-08 | 2016-12-08 | A kind of optimization method of the variation function parameter fitting of forest inventory control |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106815551B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107979817A (en) * | 2017-11-24 | 2018-05-01 | 王红军 | A kind of mobile terminal two dimension fingerprint positioning method |
| CN109241200A (en) * | 2018-08-21 | 2019-01-18 | 国网河北省电力有限公司石家庄供电分公司 | power material clustering information processing method and system |
| CN109885600B (en) * | 2019-02-25 | 2022-04-12 | 甘肃省祁连山水源涵养林研究院 | Forest vegetation growth rate analysis method and system |
| CN112085185B (en) * | 2019-06-12 | 2024-04-02 | 上海寒武纪信息科技有限公司 | Quantization parameter adjustment method and device and related product |
| CN113780515A (en) * | 2021-01-05 | 2021-12-10 | 京东鲲鹏(江苏)科技有限公司 | Data processing method, image processing method, device, storage medium and equipment |
| CN115422309B (en) * | 2022-07-07 | 2023-05-23 | 南京林业大学 | Large-scale forest age remote sensing inversion method based on neural network |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101625741A (en) * | 2009-07-07 | 2010-01-13 | 武汉大学 | Spatial configuration method for land evaluation sampling points |
| CN103282908B (en) * | 2011-05-10 | 2017-04-26 | 雪佛龙美国公司 | System and method for characterizing reservoir formation evaluation uncertainty |
| CN102567523B (en) * | 2011-12-29 | 2014-02-26 | 武汉大学 | Method for adaptively designing space sampling scheme of geographic elements with aggregated distribution characteristic |
| CN102663100B (en) * | 2012-04-13 | 2014-01-15 | 西安电子科技大学 | Two-stage hybrid particle swarm optimization clustering method |
| CN102682219B (en) * | 2012-05-17 | 2016-05-25 | 鲁东大学 | A kind of SVMs short-term load forecasting method |
| CN102842043B (en) * | 2012-07-17 | 2014-12-17 | 西安电子科技大学 | Particle swarm classifying method based on automatic clustering |
-
2016
- 2016-12-08 CN CN201611121281.1A patent/CN106815551B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN106815551A (en) | 2017-06-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106815551B (en) | A kind of optimization method of the variation function parameter fitting of forest inventory control | |
| Liang et al. | High-resolution three-dimensional mapping of soil organic carbon in China: Effects of SoilGrids products on national modeling | |
| Schmidt et al. | Comparison of polynomial models for land surface curvature calculation | |
| Song et al. | Pedoclimatic zone-based three-dimensional soil organic carbon mapping in China | |
| Kangas et al. | Value of airborne laser scanning and digital aerial photogrammetry data in forest decision making | |
| US10439594B2 (en) | Actually-measured marine environment data assimilation method based on sequence recursive filtering three-dimensional variation | |
| Garnero et al. | Comparisons between different interpolation techniques | |
| CN110598290B (en) | Method and system for predicting future hydropower generation capacity of basin considering climate change | |
| CN106355334A (en) | Farmland construction area determining method | |
| CN105893770A (en) | Method for quantifying influence on basin water resources by climate change and human activities | |
| CN109460629A (en) | A kind of cooling fan performance optimization method based on approximate model method | |
| CN111667183A (en) | Method and system for monitoring cultivated land quality | |
| Fouad et al. | Regional regression models of percentile flows for the contiguous United States: Expert versus data-driven independent variable selection | |
| Hernandez-Suarez et al. | A novel multi-objective model calibration method for ecohydrological applications | |
| CN108205718A (en) | Production method and system are surveyed in a kind of cereal crops sampling | |
| Turek et al. | Global mapping of volumetric water retention at 100, 330 and 15 000 cm suction using the WoSIS database | |
| Kaur et al. | Impact of climate change on groundwater levels in Sirhind Canal Tract of Punjab, India | |
| CN110414084A (en) | A kind of semivariable function model solution method based on tri-level programming | |
| Ziadat et al. | Soil-Landscape Estimation and Evaluation Program (SLEEP) to predict spatial distribution of soil attributes for environmental modeling | |
| Lowrance et al. | EZZone-An online tool for delineating management zones | |
| Irwin | Assessment of the regionalization of precipitation in two Canadian climate regions: A fuzzy clustering approach | |
| Govindarajan et al. | A scalable algorithm for dispersing population | |
| Jang et al. | Development of an EPIC parallel computing framework to facilitate regional/global gridded crop modeling with multiple scenarios: A case study of the United States | |
| CN108510134A (en) | A kind of method and system of determining Geological Variable tantile | |
| CN107291798A (en) | A kind of extracting method and system of geochemistry data abnormal information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190910 Termination date: 20211208 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |